Segment Anything Model, every mention
26 scenes, the whole family · ← back to Segment Anything Model
tap a year for its mentions
every year anyone Joseph Nelson 51Nikhila Ravi 46Shawn Wang 42Isaac Robinson 7Soumith Chintala 1
Verbatim, from the transcripts: the passages where Segment Anything Model comes up
Inside xAI: Building Grok Imagine in 3 Months, Videogen vs World Models, and Video Agents— Ethan He
- ▶ 32:38 Shawn Wang Annual, uh, segment anything release.
SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow)
- ▶ 0:03 unnamed speaker Okay, we're here in the remote studio with the grand return of the Roboflow and Latent Space and SAM combo. 6 times in the scene
- ▶ 5:40 Nikhila Ravi So just to start with like, what is SAM three? 5 times in the scene
- ▶ 6:21 Nikhila Ravi But essentially, idea of a concept prompt opens up the ability to find all instances of an object category without having to manually click on every single instance, as you would have had to do if you were using SAM-II or SAM-I.
- ▶ 13:39 Joseph Nelson As well as breadth of uses that we see with models like SAM in production. 10 times in the scene
- ▶ 14:30 Joseph Nelson And we've seen basically a hundred and six million kind of smart poly created examples that are, that are SAM one, two, or three powered. 2 times in the scene
- ▶ 18:32 unnamed speaker Uh, I was just so happily surprised when I was visiting the CZI Imaging Institute for, in preparation for our pod with, uh, Mark, that they were using SAM in imaging the human cell. 3 times in the scene
- ▶ 28:18 Nikhila Ravi But essentially, as I mentioned, SAM-III, we constrain the text input to these atomic visual concepts like 22 times in the scene
- ▶ 50:46 Joseph Nelson One thing that might be useful actually to discuss with some of our time is we talked a little bit about how SAM three and MLMs will play nicely together, but there's probably like a greater discussion about how SAM three fits into the… 2 times in the scene
- ▶ 56:52 Joseph Nelson Sam-III is an incredibly powerful piece of work, um, and it's open source as a part of, uh, now MSL. 12 times in the scene
- ▶ 1:03:10 Joseph Nelson One of the things that we wanted to discuss was like where to, um, use SAM and discover how to build with SAM. 3 times in the scene
- ▶ 1:14:03 Joseph Nelson We, uh, we set out to be one of the best places, if not the best place to build with SAM III and the SAM family models. 3 times in the scene
Priscilla Chan and Mark Zuckerberg: Frontier AI + Virtual Biology To Solve All Diseases
- ▶ 10:28 unnamed speaker Uh, says he's a biologist, but you know, I think he's using models like Sam from, from Meta.
Best of 2024 in Vision [LS Live @ NeurIPS]
- ▶ 1:28 Isaac Robinson And then we're also going to talk about SAM two, which applies the SAM strategy to video, and then how debtors are the improvements in 2024 to debtors that are making them a Pareto improvement to yellow base models.
- ▶ 7:55 Isaac Robinson The next, so, next paper I wanted to talk about is SAM. 6 times in the scene
[Paper Club] Embeddings in 2024: OpenAI, Nomic Embed, Jina Embed, cde-small-v1 - with swyx
- ▶ 33:35 unnamed speaker Yeah, but Sam is for segmentation. 5 times in the scene
Segment Anything 2: Memory + Vision = Object Permanence — with Nikhila Ravi and Joseph Nelson
- ▶ 0:08 Shawn Wang Our first, one of our very first viral podcasts was Segment Anything One with Joseph. 3 times in the scene
- ▶ 3:39 Shawn Wang Does that also mirror your, we know your story about going into, into vision, but like in the past year, since we did our podcast on Sam, um, what's been the impact that you've seen? 21 times in the scene
- ▶ 18:17 Nikhila Ravi With the original SAM, we put a lot of effort in building like a high quality demo. 13 times in the scene
- ▶ 23:48 Joseph Nelson So again, I can give some context into one key area that Nikola, you mentioned earlier, which is SAM has made the decision, both SAM-I and SAM-II, to be class agnostic in terms of its predictions, and that you then have the ability to have… 13 times in the scene
- ▶ 31:58 Joseph Nelson Can I bring up one limitation of SAM? 6 times in the scene
- ▶ 37:03 Nikhila Ravi We started with just SAM. 5 times in the scene
- ▶ 40:13 Shawn Wang I cannot end this podcast without talking about the architecture because this is your effectively the, the sort of research level, architecture level innovation that enabled what I've been calling object permanence for Sam and it's memory… 6 times in the scene
- ▶ 47:55 Shawn Wang Joseph already hinted at, like, you know, our interest in Sam and the future of Sam, and obviously you're the best person to ask about that. 8 times in the scene
Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI
- ▶ 1:01:59 Soumith Chintala FICE is one, Segment Anything, Detectron, Detectron II, Denspos.
Ep 18: Petaflops to the People — with George Hotz of tinycorp
- ▶ 1:05:27 Shawn Wang Uh, specifically, anything in computer vision that you think, uh, our, our second most popular episode ever was about segment anything coming out of, uh, Facebook, which is, as far as I understand, the state of the art in computer vision,… 3 times in the scene